Prediction Model of Average Temperature based on Characteristic of Urban-space Using LSTM and GRU: The Case of Wonju City

LEE WOOSEOP; Hyungkyoo Kim

doi:10.15793/kspr.2021.109..006

As the annual average temperature continues to rise due to climate change caused by global warming, the incidence of heat diseases and the number of deaths are also increasing, which is expected to require various alternatives and research. In this study, the average temperature rise-related variables are extracted through statistical analysis for Wonju City, where the average temperature increase rate and change are high, and the average temperature is predicted by utilizing deep learning-based LSTM and GRU based on the extracted variables. Three models were extracted through correlation and regression analysis for 26 variables collected based on prior research consideration, based on which LSTM and GRU analysis were conducted. The analysis showed the lowest MSE of LSTM – 0.4399(2.94°C), GRU – 0.4444(2.97°C) in the third model with 12 variables, with little MAE difference between validation and test data. This study is significant in that it extracted variables through statistical analysis and predicted average temperature rise using deep learning as a data acquisition method for adapting the annual average temperature rise problem. In addition, it is expected that urban space factors that affect the average temperature rise in Wonju City will be extracted along with predicting the trend of average temperature change, and appropriate measures will be prepared to take into account regional impact factors, not uniform climate change adaptation.

Citation status

KCI Citation Counts (2)
열림/닫힘 버튼
REFERENCES (32)
열림/닫힘 버튼
* 2021년 이후 발행 논문의 참고문헌은 현재 구축 중입니다.

[journal] 고동원 / 2019 / How the Neighborhood Environment Characteristics Affect the Urban Heat Island Effect in Seoul, Korea / 도시설계 / 한국도시설계학회 20(3) : 55~67 / https://doi.org/10.38195/judik.2019.06.20.3.55

[other] 기상청 / 2018 / 한반도 100년의 기후변화 / 기상청

[report] 기상청 / 2020 / 한국기후변화평가보고서 / 기상청

[web] / 기상청 날씨누리 / https://www.weather.go.kr/

[web] / 원주통계정보 / https://stat.wonju.go.kr

[confproc] 김장경 / 2019 / 공공 빅데이터를 이용한 폭염취약성 지수 개발에 관한 연구 / 대한토목학회 정기학술대회

[confproc] 김진아 / 2015 / 제주의 과거와 미래폭염 및 열대야일수 분석 / 한국기상학회 추계학술대회 논문집 : 876~877

[journal] 김학열 / 2003 / The Impacts of Urban Environmental Factors on air Temperatures in Seoul / 국토계획 / 대한국토·도시계획학회 38(5) : 259~269

[journal] 박경훈 / 2016 / Analysis on the Effects of Land Cover Types and Topographic Features on Heat Wave Days / 한국지리정보학회지 / 한국지리정보학회 19(4) : 76~91 / https://doi.org/10.11108/kagis.2016.19.4.076

[journal] 송봉근 / 2020 / Analysis of Relationship between the Spatial Characteristics of the Elderly Population Distribution and Heat Wave based on GIS - focused on Changwon City - / 한국지리정보학회지 / 한국지리정보학회 23(3) : 68~84 / https://doi.org/10.11108/kagis.2020.23.3.068

[web] / 에어코리아 / https://www.airkorea.or.kr/

[journal] 오규식 / 2005 / The Relationship between Urban Spatial Elements and the Urban Heat Island Effect / 도시설계 / 한국도시설계학회 6(1) : 47~63

[thesis] 오진우 / 2020 / 도시환경특성에 따른 딥러닝 기반 도시열섬현상 예측: 서울 지역을 중심으로 / 석사 / 경희대학교

[journal] 유동수 / 2020 / A Simple Program Improving Uncertainly Average Temperature and Growing Degree Days based on RCP Scenario / 한국기후변화학회지 / 한국기후변화학회 11(2) : 113~122 / https://doi.org/10.15531/KSCCR.2020.11.2.113

[journal] 윤진일 / 2002 / Urbanization Effect on the Observed Warming in Korea during the Recent Half Century / 한국농림기상학회지 / 한국농림기상학회 4(1) : 58~63

[journal] 이슬기 / 2011 / A Predictive Model for Urban Temperature using the Artificial Neural Network / 국토계획 / 대한국토·도시계획학회 46(1) : 129~142

[journal] 이승호 / 2011 / The Impacts of Urbanization on Changes of Extreme Events of Air Temperature in South Korea / 대한지리학회지 / 대한지리학회 46(3) : 257~276

[journal] 이재호 / 2011 / 기상 관측 자료를 이용한 강릉의 기후변화 추세 분석 / 한국기후변화학회지 2(2) : 133~141

[journal] 장재연 / 2009 / 기후변화, 지구온난화가 인체 건강에 미치는영향 / 대우재단 지식의 지평 6 : 159~175

[confproc] 정용진 / 2019 / GRU 를 이용한 미세먼지 (PM10) 농도 예측 모델 / 한국정보통신학회 종합학술대회 논문집 23(2) : 644~646

[confproc] 조경우 / 2019 / LSTM 을 이용한PM10 미세먼지 농도 예측 / 한국정보통신학회 종합학술대회논문집 23(2) : 632~634

[confproc] 조수현 / 2020 / 풍향풍속과미세먼지의 상관관계 분석과 LSTM 을 이용한 미세먼지 예측 / 한국정보과학회 학술발표논문집 : 1649~1651

[journal] 차영화 / 2009 / The Effects of Urban Land Use and Land Cover Characteristics on Air Temperature in Seoul Metropolitan Area / 서울도시연구 / 서울연구원 10(4) : 107~120

[journal] Bengio, Y. / 1994 / Learning long-term dependencies with gradient descent is difficult / IEEE Transactions on Neural Networks 5(2) : 157~166 / 10.1109/72.279181

[web] Cho, K / 2014 / phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 / https://arxiv.org/abs/1406.1078v3

[web] Chung, J / 2014 / Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 / https://arxiv.org/abs/1412.3555v1

[book] Hair, J. F. / 1995 / Multivariate Data Analysis with Readings / Prentice Hall

[journal] Hochreiter, S / 1997 / Long short-term memory / Neural Computation 9(8) : 1735~1780

[journal] Hochreiter, S / 1998 / Recurrent neural net learning and vanishing gradient / International Journal of Uncertainity, Fuzziness and Knowledge-Based Systems 6(2) : 107~116

[web] Karpathy, A / 2015 / Visualizing and understanding recurrent networks. arXiv preprint arXiv:1506.02078 / https://arxiv.org/abs/1506.02078v2

[book] Rea, L. M / 2014 / Designing and Conducting Survey Research: A comprehensive guide / John Wiley & Sons

[web] Ringle, C. M / 2015 / SmartPLS 3. Bönningstedt: SmartPLS / http://www.smartpls.com

KJC Korea
Journal Central

Statistics

Tools

Sharing

Issue List

Citation status